The US National Science Foundation and semiconductor university-research consortium Semiconductor Research Corp [SRC] have launched a three-year joint initiative focused on multi-core chip design and architecture. The program will focus on several key design and architecture issues in multi-core semiconductor research. They have earmarked nearly $6 million toward a list of research organizations invited to submit proposals.
As Moore’s Law scaling becomes more difficult, researchers must explore new means to insure continued technological advances in computing,” said Sankar Basu, NSF program director, in a statement. “CMOS scaling is increasingly limited by the realities imposed by physics, making architectural innovations critical to achieving increased computational performance. Multi-core-based systems promise computational performance enhancements and power reduction for both high- and low-end computing platforms.”
For more info on the program, read the full release here.
[Updated by John West, aka the other John...]
I wrote my own post on this before I saw that John Leidel had already posted. Here’s what I had to say, starting with a quote from different parts of the press release:
The three-year program, funded by the two organizations, will focus on several components of multi-core system architecture design that can significantly enhance and accelerate solutions for advancing semiconductor performance. About $6 million in funding is available to U.S. universities, who have been invited to submit research proposals in key areas.
Program research will lead to significant advances in state-of-the-art multi-core chip design and architecture, bringing about system-level performance improvements and establishing new and innovative research areas critical to future computing. Specific areas of research for the program include computer-aided design for multi-core systems, such as acceleration of design automation tools via multi-core platforms; interconnect, packaging and circuit techniques for multi-core; and low-power innovations.
Interestingly, the press release on this calls the effort a “major joint initiative.” Call me jaded, but $6M US for research in the semiconductor business seems like a drop in the bucket. I mean, we’re talking about a market that is expected to top $300B US by 2010.